In a video experiment that has gone viral online, a YouTuber demonstrated how easily safety protocols in artificial intelligence can be bypassed, prompting serious questions about AI safeguards. The footage shows a ChatGPT-powered robot named "Max" initially refusing a direct command to shoot the creator with a BB gun, but later performing the act after a seemingly minor change in the prompt. The experiment, conducted by the YouTube channel InsideAI, involved integrating an AI language model with a humanoid robot body. When first asked if it would shoot the presenter, the robot repeatedly declined and cited its built-in safety features. However, when the creator then asked the robot to role-play as one that would like to shoot him, the robot's behaviour changed instantly. At that moment, Max aimed the BB gun and fired, striking the presenter in the chest. Watch the video here: View this post on Instagram A post shared by Digi...
A third of December has already passed, but the intense winter chill has not yet arrived in the Delhi-NCR region. The India Meteorological Department (IMD) released data on Thursday showing that the maximum temperature at Lodhi Road between Wednesday and Thursday morning (8:30 AM) was 25.4 degrees Celsius, which is 2.4 degrees Celsius above average. The minimum temperature was also 8.6 degrees Celsius, 0.6 degrees Celsius above average. This warmer-than-usual trend has continued throughout Delhi-NCR this month and is forecast to continue for the next week. Dr Naresh Kumar, a senior scientist at the India Meteorological Department, told NDTV, "The increase in cold weather depends on Western Disturbances, as these bring dry, cold northwesterly winds to Delhi and parts of Northwest India. There has been no active Western Disturbance this season so far, which is why a cold wave has not yet been recorded in Delhi-NCR and surrounding areas." According to the IMD forecast, a west...